harveyslash/Facial-Similarity-with-Siamese-Networks-in-Pytorch：实现具有对比损失的暹罗网络以进行相似学习 - 中文解读

项目介绍

harveyslash/Facial-Similarity-with-Siamese-Networks-in-Pytorch 是一个托管在 GitHub 上的开源项目，主要使用 Jupyter Notebook 编写，采用 MIT License 许可证，目前获得 989 个 Star、271 次 Fork。

仓库全名: harveyslash/Facial-Similarity-with-Siamese-Networks-in-Pytorch

README 摘要

Facial Similarity with Siamese Networks in Pytorch You can read the accompanying article at https://hackernoon.com/one-shot-learning-with-siamese-networks-in-pytorch-8ddaab10340e The goal is to teach a siamese network to be able to distinguish pairs of images. This project uses pytorch. Any dataset can be used. Each class must be in its own folder. This is the same structure that PyTorch's own image folder dataset…

完整内容见 GitHub 原始 README 或本页。

常见问题

Facial-Similarity-with-Siamese-Networks-in-Pytorch 用什么语言开发？

主要使用 Jupyter Notebook 编写，采用 MIT License 许可证，目前有 989 个 Star。

Facial-Similarity-with-Siamese-Networks-in-Pytorch 可以免费商用吗？

仓库采用 MIT License 许可证，可免费使用与修改，商业使用请遵守许可证条款（例如保留版权声明与许可声明）。

如何获取 Facial-Similarity-with-Siamese-Networks-in-Pytorch 的源码？

可以直接克隆仓库：git clone https://github.com/harveyslash/Facial-Similarity-with-Siamese-Networks-in-Pytorch.git，默认分支为 master；安装与运行步骤见仓库 README。

Facial-Similarity-with-Siamese-Networks-in-Pytorch 最近还在维护吗？

仓库最近一次更新为 2020年7月16日，当前有 12 个未关闭 Issue；Star 数为 989，可作为社区活跃度的参考。

关于

GitHub 原始描述（英文）

Implementing Siamese networks with a contrastive loss for similarity learning

deep-learning face-recognition neural-network pytorch pytorch-tutorial siamese-network

MIT License
989 Stars
271 Forks
21 Watching

描述取自 GitHub 官方 API，保持仓库作者书写的原文。

简要分析

热度分

1552

价值分

676

活跃状态

活跃

语言占比

Jupyter Notebook

贡献者

harveyslash

luosyx

Choco31415

Fanshia

shashankp

dshahrokhian

Facial Similarity with Siamese Networks in Pytorch

You can read the accompanying article at https://hackernoon.com/one-shot-learning-with-siamese-networks-in-pytorch-8ddaab10340e

The goal is to teach a siamese network to be able to distinguish pairs of images. This project uses pytorch.

Any dataset can be used. Each class must be in its own folder. This is the same structure that PyTorch’s own image folder dataset uses.

Update: Looking for contributor (July 2020)

If you would like to be a part of this projec, please head to https://github.com/harveyslash/Facial-Similarity-with-Siamese-Networks-in-Pytorch/issues/35

Converting pgm files (if you decide to use the AT&T dataset) to png

Install imagemagick
Go to root directory of the images
Run find -name "*pgm" | xargs -I {} convert {} {}.png

Installing the right version of PyTorch

This project is updated to be compatible with pytorch 0.4.0

This project requires python3.6

评论

暂无评论